Iterative Learning-Based Robotic Controller With Prescribed Human–Robot Interaction Force

In this article, an iterative-learning-based robotic controller is developed, which aims at providing a prescribed assistance or resistance force to the human user. proposed controller, characteristic parameter of upper limb movement first learned by robot using measurable interaction force, recursive least square (RLS)-based estimator, and Adam optimization method. Then, desired trajectory can be obtained, tracking supply human’s with force. Using automatically adjusts its reference embrace differences between different users diverse degrees characteristics. By designing performance index in form integral, potential adverse effects caused time-related uncertainty during learning process addressed. The experimental results demonstrate effectiveness method supplying Note Practitioners—This article concentrates on developing novel control technique make user presence uncertainties. applicable various scenarios human–robot interaction, e.g., it used for rehabilitation robots provide assistive resistive stroke patients exoskeleton completing heavy-load tasks. Moreover, tailored according their needs task objectives. Consequently, serve has promising perspective automation.